EP3806009A1 - Procédé d'évaluation d'un itinéraire sélectionné, système d'évaluation d'itinéraire et programme informatique - Google Patents

Procédé d'évaluation d'un itinéraire sélectionné, système d'évaluation d'itinéraire et programme informatique Download PDF

Info

Publication number
EP3806009A1
EP3806009A1 EP20199511.5A EP20199511A EP3806009A1 EP 3806009 A1 EP3806009 A1 EP 3806009A1 EP 20199511 A EP20199511 A EP 20199511A EP 3806009 A1 EP3806009 A1 EP 3806009A1
Authority
EP
European Patent Office
Prior art keywords
route
evaluation
feature
sections
route sections
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP20199511.5A
Other languages
German (de)
English (en)
Inventor
Amit Chaulwar
Torben Fischer
Johannes Stiller
Johannes Reichold
Anatol Weidenbach
Qiaoling ZHANG
Jagmal Singh
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZF Friedrichshafen AG
Original Assignee
ZF Friedrichshafen AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ZF Friedrichshafen AG filed Critical ZF Friedrichshafen AG
Publication of EP3806009A1 publication Critical patent/EP3806009A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/60—Positioning; Navigation

Definitions

  • the invention relates to autonomous vehicles and autonomous driving, in particular to a method and a route evaluation system for identifying routes that are suitable for autonomous operation.
  • the invention also relates to a computer program.
  • An automated / autonomous vehicle with an autonomy level of four or more is able to carry out all driving functions autonomously in certain traffic situations.
  • L4 vehicle an autonomous vehicle with an autonomy level of four or more
  • This system works in a structured environment, there are many features, such as pedestrian crossings, traffic signs, bus stops, etc., that affect the operation of an L4 automated vehicle.
  • these features can have different forms in different places for which the driving functions of the L4 automated vehicle must be adapted. This creates an overwhelming number of driving situations and makes it impossible to directly develop general driving functions that work in all driving situations.
  • the DE 10 2016 116 272 A1 discloses a computer-implemented method comprising: obtaining data from a first plurality of road segments already approved for one or more autonomous operations at an autonomous level; Generating a road segment template based on this data; and redesigning a second plurality of road segments that have not been approved for the one or more autonomous operations at the autonomous level based on the road segment template to provide a plurality of redesigned road segments.
  • This object is achieved by a method for evaluating a selected route for using the route in an autonomously operated vehicle with the features of claim 1 and a route evaluation system with the features of claim 11.
  • Feature-based route sections are route sections created for an earlier route, for example, which, in addition to the relevant road section, also contain additional information in the form of recognized infrastructure features for the route section, such as, for example, priority information on a kinking road.
  • a feature-based route section is, for example, a traffic node, with specific node-related infrastructure features having been added to the traffic node. If the traffic junction is, for example, a road intersection, right of way rules, lane markings, number of lanes, etc. can be stored.
  • Such infrastructure features influence the driving of an autonomous vehicle along a route.
  • Traffic situations are situations in relation to these feature-based route sections, for example the traffic junction, that is to say for example the road intersection.
  • a traffic situation describes the entirety of the circumstances without taking other road users into account.
  • Traffic scenarios supplement the information of a traffic situation with additional information about all road users.
  • Driving functions are then the instructions for operation, for example longitudinal guidance / lateral guidance of the vehicle, in this traffic situation.
  • feature-based route sections are developed for individual routes that represent a series of successive elementary traffic situations.
  • a function catalog is provided in which a respective driving function is stored for the traffic situations occurring on feature-based route sections.
  • the situation assessment is carried out by using the function catalog to identify first feature-based route sections not included in the function catalog by a computing unit. For example, there is a roundabout along the selected route which is not available in the function catalog or for which no traffic situation with a driving function is stored in the function catalog.
  • the first feature-based route sections not included in the function catalog can be defined as "gaps" if no traffic situation with driving functions is stored for them in the function catalog.
  • the computer-aided subjective assessment is carried out on the basis of provided video and / or image data of the selected route.
  • second infrastructure features that are not included in the situation assessment have been recognized, identified in the video and / or image data.
  • Second infrastructure features are, for example, speed limiters, traffic islands that are not listed in the digital map or are very difficult to extract and therefore were not recorded in the situation assessment.
  • the evaluation of the simulated traffic scenarios is carried out in that the function catalog, that is to say the various traffic-situation-dependent driving functions present in the function catalog, are applied to the traffic scenarios.
  • This allows "gaps" to be identified, for example, as problems in the existing catalog of functions.
  • traffic scenarios are generated along the route.
  • parameters such as position, speed, acceleration, size, etc. of the road users can be changed stochastically.
  • An evaluation of the traffic scenarios is then carried out in which the function catalog, that is to say the various traffic-situation-dependent driving functions available in the function catalog, are applied to the traffic scenarios. This allows "gaps" to be identified, for example, as problems in the existing catalog of functions.
  • an exact and thorough gap analysis based on the situation assessment, the computer-aided subjective assessment and the simulative assessment for a selected route is specified. If the selected route proves not to be drivable with an autonomous vehicle, or only at high cost and development effort, this can be recognized in good time.
  • the catalog of functions can be updated with preference.
  • the sensor data are preferably generated continuously.
  • the sensor data are preferably continuously collected during the entire operating time of the automated L4 vehicle, which means that the sensor data are preferably logged each time the vehicle is used on the route and stored, for example, in a cloud.
  • the sensor data are preferably logged each time the vehicle is used on the route and stored, for example, in a cloud.
  • further errors in the function catalog can be found, since a large amount of data is available.
  • further deficiencies can thus be identified, for example in the vehicle's detection system and / or when the function catalog is applied to the traffic scenarios detected by the sensor data provided.
  • the video and / or image data of the selected route are preferably provided by a detection system of the vehicle.
  • a plurality of video and / or image data of the selected route for different weather data are preferably provided by the detection system of the vehicle. This means that a large and extensive amount of data can be made available.
  • the driving functions and / or vehicle functions on which the autonomous vehicle is based are preferably checked at least partially with the aid of a computer using the video / image data. This enables safe, autonomous operation to be achieved.
  • the traffic scenarios are preferably generated virtually, and thus inexpensively, in the computing unit.
  • a vehicle with all sensors collects real sensor data along the route, preferably in different weather and traffic conditions.
  • sensor data for interesting traffic scenarios with different road users are recorded. If necessary, these traffic scenarios are replicated and data is collected using the actual road users on the route.
  • the collected data are preferably analyzed afterwards, in particular offline, in order to identify deficiencies.
  • the video and / or image data of the selected route can be provided by the detection system of one or more road users in a cloud. This means that an extensive amount of data can be made available quickly.
  • Different routes are preferably specified by a starting point and a destination point and waypoints in between, the automated situation assessment being used to prioritize the different routes based on this given starting point and destination and the waypoints in between for further evaluation.
  • the advantages of the method can also be transferred to the route evaluation system.
  • the subjective evaluation preferably includes a manual evaluation.
  • the card is preferably designed as a high definition (HD) card.
  • HD high definition
  • the object is achieved by a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method as described above.
  • a function catalog is provided. This includes feature-based route sections, with each feature-based route section being assigned different traffic situations with the respective driving functions tailored to the traffic situation.
  • Feature-based route sections are route sections created for an earlier route, for example, which, in addition to the relevant road section, also contain additional information in the form of infrastructure features for the route section, such as right of way information on a kinking road.
  • infrastructure features are, for example, pedestrian crossings, traffic signs, bus stops, etc.
  • a feature-based route section is, for example, a traffic node, with specific node-related infrastructure features having been added to the traffic node. If the node is, for example, an intersection, right of way rules, lane markings, number of lanes, etc. can be stored.
  • a selected route that is to be traveled by an autonomously operated vehicle is provided.
  • This route must be rated as suitable so that an autonomous vehicle can drive on it in the autonomous operating mode.
  • the vehicle can preferably be operated as a vehicle with autonomy level four and higher. From an autonomy level of four, the vehicle is permanently taken over by the vehicle.
  • the selected route is a permanently predetermined route, i.e. H. not only the starting point and destination are given, but the route itself is given.
  • a third step S3 the selected route is divided into feature-based first route sections. This is done on the basis of first infrastructure features such as crossings, etc. These first infrastructure features are automatically extracted from a digital map along the selected route, for example via a corresponding API (programming interface) by a computing unit.
  • first infrastructure features such as crossings, etc.
  • the feature-based first route sections are generated automatically on the basis of these first infrastructure features.
  • the digital map can be designed as HD maps (high definition map).
  • HD maps high definition map
  • Such a high-resolution map (HD maps) comprises an extremely precise representation of roads, which contains infrastructure features such as lane models, traffic signs and lane geometries with an accuracy of a few centimeters.
  • a fourth step S4 an automated situation assessment is then carried out in that first feature-based route sections that are not included in the function catalog are identified by a computing unit on the basis of the function catalog. This can be done, for example, by simply comparing the individual route sections with those route sections that are available in the function catalog.
  • the first feature-based route sections not included in the function catalog can be defined as "gaps" if different traffic situations with driving functions have to be stored for these in the function catalog.
  • the automated situation assessment thus quasi evaluates the filling / removal of these gaps.
  • This automated situation assessment leads to a first result E1.
  • the automated situation assessment results in an assessment of the static environment of the feature-based first route sections not included, along the selected route.
  • some of the identified gaps can be closed by changing the infrastructure on the selected route, such as clearly identifying the lane, distance from parking spaces, changing the location of the charging station, etc.
  • This first result E1 thus represents a first evaluation factor for the “gap” for the selected route. Since the situation assessment is carried out automatically, it can be carried out very quickly and inexpensively.
  • a computer-aided subjective assessment is carried out on the basis of the provided video and / or image data of the selected route.
  • second infrastructure features which were not recognized in the situation assessment, are identified in the video and / or image data.
  • Second infrastructure features are, for example, speed limiters, traffic islands that are not listed in the digital map or are very difficult to extract and therefore were not recorded in the situation assessment.
  • Second infrastructure features can preferably also be other new relevant infrastructure features that are required for the selected route.
  • the route in company plants requires the detection of special vehicles such as forklifts. These cannot be extracted from digital maps.
  • second feature-based route sections can be generated.
  • the first route sections which have these second identified infrastructure features, are subdivided, for example, into a first route section and a second route section, the second route section having the second infrastructure feature, or are redistributed as second route sections.
  • a plurality of video and / or image data of the selected route are preferably provided under different weather conditions.
  • This computer-aided subjective assessment leads to a second result E2.
  • This second result E2 represents a further evaluation factor for the new "gaps" for the selected route. If necessary, some of the recognized gaps can be caused by an infrastructure change on the selected route, such as a clear identification of the lane, distance from parking spaces, change of the location of the Charging station etc. are closed.
  • the first route sections are completed and / or corrected using the video and / or image data if the first infrastructure features identified by the situation assessment are incomplete and / or incorrect , and a new situation assessment is carried out on the basis of the corrected or completed first route sections. This leads to an improved assessment of the situation.
  • a seventh step S7 which preferably runs parallel to the sixth step S6 and the fifth step S5, the vehicle functions on which the autonomous vehicle is based are checked and evaluated with the aid of a computer using the video / image data. For example, the lane recognition function is evaluated in order to check whether a lane marking is not correctly recognized.
  • This computer-aided assessment leads to a third result E3.
  • This third result E3 represents a further evaluation factor for the selected route.
  • a simulative evaluation is carried out by generating traffic scenarios in relation to all feature-based route sections of the route and a subsequent evaluation of all traffic scenarios using the traffic-situation-dependent driving functions and existing traffic situations, which are taken from the function catalog.
  • step S8 all possible traffic scenarios along the selected route are simulated by stochastically changing the parameters such as position, speed, acceleration, size, trajectory, etc. of the road users. As a result, all possible constellations are covered cost-effectively, since a simulation is very cost-effective compared to imitating the scenarios on test areas.
  • a detailed route map of the selected route or, for example, an HD map can be used for the simulative evaluation.
  • the simulated traffic scenarios are then evaluated by applying the function catalog, i.e. the various traffic-situation-dependent driving functions available in the function catalog to the traffic scenarios.
  • a ninth step S9 which can be carried out as an alternative or in addition to the eighth step S8, traffic scenarios relating to all feature-based route sections of the route are generated using sensor data generated by the vehicle along the route, and a subsequent evaluation of all traffic scenarios is generated under Use of the traffic situation-dependent driving functions, which are taken from the function catalog, carried out.
  • sensor data are preferably generated under different weather conditions.
  • deficiencies in the detection of the sensor data for example deficiencies in the detection system of the vehicle, are recognized, which is included as a fourth result E4 in the overall assessment.
  • a tenth step S10 the results E1 to E4, which were compiled in the individual previous results, are evaluated as a pre-deployment evaluation (planning phase process).
  • the gaps identified in the various steps prior to deployment in the form of newly recognized traffic situations that are not stored in the vehicle catalog and / or missing route sections in the vehicle catalog and / or defects are compiled and assessed.
  • FIG 2 shows a second embodiment of the method according to the invention. In its steps A1 to A10, this is the same as steps S1 to S10.
  • the procedure in FIG 2 In addition to the pre-deployment evaluation, it also includes a post-deployment evaluation (follow-up process).
  • step A11 the identified gaps and defects are first rectified and the vehicle travels on the selected route.
  • a test driver can initially be used until the autonomously driving vehicle has achieved the desired automated driving behavior.
  • the sensor data of the selected route are continuously recorded by the recording system of the vehicle and stored for evaluation.
  • the sensor data can be saved in a cloud.
  • the continuous recording creates large amounts of data.
  • the method for evaluating a selected route is thus divided into two subcategories: the pre-deployment evaluation and the post-deployment evaluation (evaluation before and after provision in the vehicle).
  • the pre-deployment evaluation is carried out before the automated vehicle with the further developed function catalog, in which the gaps found by the pre-deployment evaluation have been remedied, is deployed on the selected route.
  • the post-deployment evaluation the vehicle is actually used on the route.
  • the post-deployment evaluation can be understood as the continuous lifelong detection of errors / gaps / deficiencies.
  • FIG 3 shows a further embodiment of the method according to the invention graphically in a block diagram.
  • the method is also divided into two sub-categories: the pre-deployment evaluation and the post-deployment evaluation (evaluation before and after provision in the vehicle).
  • the function catalog is provided in a step V1. This includes feature-based route sections, with each feature-based route section being assigned different traffic situations with the respective driving functions tailored to the traffic situation.
  • a selected route for using the route in an autonomously operated vehicle is provided.
  • the selected route is specified by a starting point and a destination point and waypoints in between.
  • a third step V3 the route initially selected is divided into feature-based first route sections. This is done using first infrastructure features such as crossings, etc. These first infrastructure features are automatically extracted from a digital map along the selected route by a computing unit, for example via the corresponding API (programming interface).
  • first infrastructure features such as crossings, etc.
  • a fourth step V4 an automated situation assessment is carried out in that first feature-based route sections that are not included in the function catalog are identified by a computing unit on the basis of the function catalog. This can be done, for example, by simply comparing the individual route sections with those route sections that are available in the function catalog.
  • the first feature-based route sections not included in the function catalog are defined as "gaps" if different traffic situations with respective driving functions have to be stored for these in the function catalog. Since the route is predefined by the starting point, destination and the waypoints in between, the automated situation assessment can therefore be used to prioritize different routes based on this given starting point and destination and the waypoints in between for further evaluation based on the size of the detected gap .
  • the automated situation assessment represents a first evaluation factor for the "gap" for the selected route. Since the situation assessment is carried out automatically, it can be carried out very quickly and inexpensively.
  • some of the identified gaps can be closed by changing the infrastructure on the selected route, such as clearly identifying the lane, distance from parking spaces, changing the location of the charging station, etc.
  • a computer-aided subjective assessment is carried out on the basis of the video and / or image data provided for the selected route.
  • second infrastructure features which were not recognized in the situation assessment are identified in the video and / or image data.
  • second feature-based route sections can be generated.
  • the first route sections which have these second identified infrastructure features, are subdivided, for example, into a first route section and a second route section, the second route section having the second infrastructure feature, or are redistributed as second route sections. This is preferably done manually as well as with the aid of a computer.
  • the computer-aided subjective assessment identifies "gaps" in the catalog of functions for the selected route.
  • some of the identified gaps can be closed by changing the infrastructure on the selected route, such as clearly identifying the lane, distance from parking spaces, changing the location of the charging station, etc.
  • the first route sections are completed and / or corrected using the video and / or image data if the first infrastructure features identified by the situation assessment are incomplete and / or incorrect , and a new situation assessment is carried out on the basis of the corrected or completed first route sections.
  • a seventh step V7 which preferably runs parallel to the sixth step V6 and the fifth step V5, the driver assistance functions and / or vehicle functions on which the autonomous vehicle is based are checked and evaluated with the aid of a computer using the video / image data.
  • a simulative evaluation is carried out by generating traffic scenarios in relation to all feature-based route sections of the route and a subsequent evaluation of all traffic scenarios using the traffic-situation-dependent driving functions and existing traffic situations, which are taken from the function catalog.
  • step V8 all possible scenarios along the selected route are simulated by stochastically changing the parameters such as position, speed, acceleration, size, trajectory, etc. of the road users.
  • a ninth step V9 the traffic scenarios with respect to all feature-based route sections of the route are generated using sensor data generated by the vehicle along the route, and a subsequent evaluation of all traffic scenarios is carried out using the traffic-situation-dependent driving functions, which are taken from the catalog of functions. These can also be used in the simulative evaluation.
  • deficiencies in the detection of the sensor data such as deficiencies in the detection system of the vehicle, are detected.
  • some of the identified gaps can be closed by changing the infrastructure on the selected route, such as clearly identifying the lane, distance from parking spaces, changing the location of the charging station, etc.
  • a tenth step V10 the gaps that have been compiled in the individual previous results are evaluated as a pre-deployment evaluation (planning phase process).
  • the gaps identified in the various steps prior to deployment in the form of newly recognized traffic situations that are not stored in the vehicle catalog and / or missing route sections in the vehicle catalog and / or defects are compiled and assessed.
  • step V11 the identified gaps and deficiencies are first rectified and the vehicle travels on the selected route.
  • the sensor data of the selected route are continuously recorded by the recording system of the vehicle and stored for evaluation.
  • FIG 4 has a further embodiment of the method, which is very similar to the method in FIG 3 is ajar. Therefore only the differences should be mentioned here FIG 3 explained.
  • the simulative evaluation (ninth step V9) is carried out.
  • a subsequent evaluation of all traffic scenarios is carried out using the traffic situation-dependent driving functions, which are taken from the function catalog.
  • the simulative evaluation can be used to identify "gaps", for example problems in the existing catalog of functions.
  • deficiencies in the acquisition of the sensor data for example deficiencies in the vehicle's detection system, are detected.
  • some of the identified gaps can be closed by infrastructure changes on the selected route, such as clear identification of the lanes, changes in the distance from parking spaces, changes in the location of the charging station, etc. This is in FIG 4 shown graphically.
  • the eighth step V8 is omitted.
  • FIG 5 has a further embodiment of the method, which is very similar to the method in FIG 3 is ajar. Therefore only the differences should be mentioned here FIG 3 explained.
  • the simulative evaluation (eighth step V8) is carried out by generating traffic scenarios in relation to all feature-based route sections of the route and a subsequent evaluation of all traffic scenarios using the traffic-situation-dependent driving functions, which are taken from the function catalog.
  • step V8 all possible traffic scenarios along the selected route are simulated on a computing unit by stochastically changing the parameters such as position, speed, acceleration, size, trajectory, etc. of the road users.
  • a detailed route map of the selected route or, for example, an HD map can be used for the simulative evaluation.
  • the ninth step V9 is omitted.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)
EP20199511.5A 2019-10-11 2020-10-01 Procédé d'évaluation d'un itinéraire sélectionné, système d'évaluation d'itinéraire et programme informatique Withdrawn EP3806009A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102019215656.8A DE102019215656B4 (de) 2019-10-11 2019-10-11 Verfahren zum Bewerten einer ausgewählten Route, Routenbewertungssystem und Computerprogramm

Publications (1)

Publication Number Publication Date
EP3806009A1 true EP3806009A1 (fr) 2021-04-14

Family

ID=72717700

Family Applications (1)

Application Number Title Priority Date Filing Date
EP20199511.5A Withdrawn EP3806009A1 (fr) 2019-10-11 2020-10-01 Procédé d'évaluation d'un itinéraire sélectionné, système d'évaluation d'itinéraire et programme informatique

Country Status (2)

Country Link
EP (1) EP3806009A1 (fr)
DE (1) DE102019215656B4 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021204326A1 (de) 2021-04-30 2022-11-03 Zf Friedrichshafen Ag Verfahren sowie Server oder Steuergerät zum Ermitteln von in einem Fahrabschnitt benötigten Merkmalen eines Fahrsystems

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150253772A1 (en) * 2014-03-04 2015-09-10 Volvo Car Corporation Apparatus and method for continuously establishing a boundary for autonomous driving availability and an automotive vehicle comprising such an apparatus
US20150314780A1 (en) * 2014-04-30 2015-11-05 Here Global B.V. Mode Transition for an Autonomous Vehicle
DE102016116272A1 (de) 2015-09-02 2017-04-20 Ford Global Technologies, Llc Allgemeine zertifizierung von autonomem fahren
DE102017206343A1 (de) * 2017-04-12 2018-10-18 Robert Bosch Gmbh Verfahren zum Ermitteln von Daten eines Verkehrsszenarios
WO2018200522A1 (fr) * 2017-04-24 2018-11-01 Mobileye Vision Technologies Ltd. Systèmes et procédés de compression de données de voies
DE102017215708A1 (de) * 2017-09-06 2019-03-07 Audi Ag Verfahren und System zur Ermittlung einer Qualitätskarte für Fahrbahnmarkierungen
US20190196472A1 (en) * 2016-08-30 2019-06-27 Continental Automotive Gmbh System and method for analyzing driving trajectories for a route section
US20190294167A1 (en) * 2016-08-02 2019-09-26 Pcms Holdings, Inc. System and method for optimizing autonomous vehicle capabilities in route planning

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6467773B2 (ja) 2014-02-25 2019-02-13 アイシン・エィ・ダブリュ株式会社 経路探索システム、経路探索方法及びコンピュータプログラム
US20170356750A1 (en) 2016-06-14 2017-12-14 nuTonomy Inc. Route Planning for an Autonomous Vehicle
DE102017209346A1 (de) 2017-06-01 2019-01-10 Robert Bosch Gmbh Verfahren und Vorrichtung zur Erstellung einer fahrspurgenauen Straßenkarte

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150253772A1 (en) * 2014-03-04 2015-09-10 Volvo Car Corporation Apparatus and method for continuously establishing a boundary for autonomous driving availability and an automotive vehicle comprising such an apparatus
US20150314780A1 (en) * 2014-04-30 2015-11-05 Here Global B.V. Mode Transition for an Autonomous Vehicle
DE102016116272A1 (de) 2015-09-02 2017-04-20 Ford Global Technologies, Llc Allgemeine zertifizierung von autonomem fahren
US20190294167A1 (en) * 2016-08-02 2019-09-26 Pcms Holdings, Inc. System and method for optimizing autonomous vehicle capabilities in route planning
US20190196472A1 (en) * 2016-08-30 2019-06-27 Continental Automotive Gmbh System and method for analyzing driving trajectories for a route section
DE102017206343A1 (de) * 2017-04-12 2018-10-18 Robert Bosch Gmbh Verfahren zum Ermitteln von Daten eines Verkehrsszenarios
WO2018200522A1 (fr) * 2017-04-24 2018-11-01 Mobileye Vision Technologies Ltd. Systèmes et procédés de compression de données de voies
DE102017215708A1 (de) * 2017-09-06 2019-03-07 Audi Ag Verfahren und System zur Ermittlung einer Qualitätskarte für Fahrbahnmarkierungen

Also Published As

Publication number Publication date
DE102019215656A1 (de) 2021-04-15
DE102019215656B4 (de) 2021-07-22

Similar Documents

Publication Publication Date Title
EP3438901A1 (fr) Système de base de données de scénario de conduite d'essai pour scénarios de conduite d'essais virtuels proches de la réalité
DE102017009435B4 (de) Evaluation von Komponenten automatischer Fahrfunktionen und Fahrbahnerkennung auf unterschiedlichen Verarbeitungsstufen
WO2016150590A1 (fr) Procédé et dispositif pour surveiller une trajectoire de consigne à parcourir par un véhicule au sujet de l'absence de collision
EP3391086B1 (fr) Procédé amélioré de détermination de la construction de bord d'une chaussée pour la localisation de véhicules automobiles
DE102016207276A1 (de) Verfahren zur Freigabe einer Fahrfunktion in einem Fahrzeug
DE102019211009A1 (de) Verfahren und Computerprogramm zum Simulieren eines autonomen Fahrzeugs in einer Mehrzahl von Testfällen
EP3239903A1 (fr) Procédé et dispositif de comparaison de deux cartes comprenant des amers enregistrés
DE102018219602A1 (de) Verfahren zum Erkennen von Kartenfehlern
DE102022002334B3 (de) Verfahren zur Ermittlung und Bereitstellung von Fahrspurverläufen
DE102020200169B3 (de) Verfahren zur Zusammenführung mehrerer Datensätze für die Erzeugung eines aktuellen Spurmodells einer Fahrbahn und Vorrichtung zur Datenverarbeitung
DE102014207694A1 (de) Verfahren zum Evaluieren der Errechnung von Umfeldmodellen durch Fahrzeuge
DE102010001700A1 (de) Verfahren zur Bestimmung eines Bildes benutzter oder bekannter Streckenabschnitte
DE102018202970A1 (de) Verfahren zum Ermitteln einer topologischen Information einer Straßenkreuzung
DE102019215656B4 (de) Verfahren zum Bewerten einer ausgewählten Route, Routenbewertungssystem und Computerprogramm
DE102020110269B4 (de) Verfahren zum Ermitteln einer Informationslücke in einem Fahrspurmarkierungsmodell für ein Kraftfahrzeug sowie System zum Durchführen eines derartigen Verfahrens
EP4350660A1 (fr) Système et procédé de prédiction d'une position future d'un usager de la route
EP2153172B1 (fr) Correspondance cartographique pour applications de sécurité
DE102016224042A1 (de) Verfahren und Vorrichtung zum Überprüfen von hochgenauen Kartendaten für Fahrerassistenzfunktionen eines Kraftahrzeugs
DE102022001030B3 (de) Verfahren zur Ermittlung einer Navigationsroute für einen automatisierten Fahrbetrieb eines Fahrzeugs
DE102018218043A1 (de) Ermittlung einer Anzahl von Fahrspuren sowie von Spurmarkierungen auf Straßenabschnitten
EP3499271A1 (fr) Détermination d'une position d'un véhicule
DE102021207528A1 (de) Erkennung von Verbindungsmustern anhand von Trajektoriendaten
DE102017011982A1 (de) Verfahren zur Streckenvorausschau
WO2022122553A1 (fr) Comparaison de représentations numériques de situations de conduite d'un véhicule
DE102014204933A1 (de) Verfahren und eine Vorrichtung zur Erzeugung eines Segmentierungs-Layers

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20211015